Shortcut Learning of Large Language Models in Natural Language Understanding-Reference-Cited by-同舟云学术

Shortcut Learning of Large Language Models in Natural Language Understanding

Published:2023-12-21 Issue:1 Volume:67 Page:110-120
ISSN:0001-0782
Container-title:Communications of the ACM
language:en
Short-container-title:Commun. ACM

Author:

Du Mengnan¹,He Fengxiang²,Zou Na³,Tao Dacheng⁴,Hu Xia⁵

Affiliation:

1. New Jersey Institute of Technology, University Heights, Newark, NJ, USA

2. University of Edinburgh, Scotland

3. Texas A&M University, College Station, TX, USA

4. University of Sydney, Australia

5. Rice University, Houston, TX, USA

Abstract

Shortcuts often hinder the robustness of large language models.

Publisher

Association for Computing Machinery (ACM)

Subject

General Computer Science

Link

https://dl.acm.org/doi/pdf/10.1145/3596490

Reference52 articles.

1. Arjovsky , M. , Bottou , L. , Gulrajani , I. , and Lopez-Paz , D. Invariant risk minimization , 2019 ; arXiv:1907.02893. Arjovsky, M., Bottou, L., Gulrajani, I., and Lopez-Paz, D. Invariant risk minimization, 2019; arXiv:1907.02893.

2. Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics

3. Branco , R. , Branco , A. , Silva , J. , and Rodrigues , J . Shortcutted commonsense: Data spuriousness in deep learning of commonsense reasoning . In Proceedings of the 2021 Conf. Empirical Methods in Natural Language Processing. Branco, R., Branco, A., Silva, J., and Rodrigues, J. Shortcutted commonsense: Data spuriousness in deep learning of commonsense reasoning. In Proceedings of the 2021 Conf. Empirical Methods in Natural Language Processing.

4. Brown , T.B. et al. Language models are few-shot learners . Advances in Neural Information Processing Systems , 2020 . Brown, T.B. et al. Language models are few-shot learners. Advances in Neural Information Processing Systems, 2020.

5. Bubeck , S. and Sellke , M . A universal law of robustness via isoperimetry . Advances in Neural Information Processing Systems , 2021 . Bubeck, S. and Sellke, M. A universal law of robustness via isoperimetry. Advances in Neural Information Processing Systems, 2021.

Cited by 11 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Understanding Large Language Models;Advances in Computational Intelligence and Robotics;2024-08-30

2. Adaptive Evolutionary Computing Ensemble Learning Model for Sentiment Analysis;Applied Sciences;2024-08-04

3. Esale: Enhancing Code-Summary Alignment Learning for Source Code Summarization;IEEE Transactions on Software Engineering;2024-08

4. COMI: COrrect and MItigate Shortcut Learning Behavior in Deep Neural Networks;Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval;2024-07-10

5. Cost, Usability, Credibility, Fairness, Accountability, Transparency, and Explainability Framework for Safe and Effective Large Language Models in Medical Education: Narrative Review and Qualitative Study;JMIR AI;2024-04-23